© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 31-TRANSCODER-HP
    7. 19018
    Prev
    Next
    INDEX
    Explanations

    );č

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åħ¨è¦ĨçĽĸ
    -0.27
    ivot
    -0.25
    ing
    -0.24
    icken
    -0.24
    å®ī举
    -0.24
     complete
    -0.24
    å®Įæķ´
    -0.24
     completeness
    -0.23
    acula
    -0.23
    å®Įæķ´çļĦ
    -0.23
    POSITIVE LOGITS
    бо
    0.28
    çļĦç²¾ç¥ŀ
    0.26
    TRACT
    0.25
    öz
    0.25
    ãĥ¥
    0.24
     penc
    0.24
    '].$
    0.24
    abric
    0.23
    udence
    0.23
    ìļ°
    0.23
    Activations Density 0.004%

    No Known Activations